Brian Okorn
Carnegie Mellon University
19 Papers
105 Citations
Brian Okorn is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Computer science & Pose. The author has an hindex of 5, co-authored 19 publications. Previous affiliations of Brian Okorn include Space and Naval Warfare Systems Center Pacific & Vanderbilt University.
Chat about Author
Papers
Just Go With the Flow: Self-Supervised Scene Flow Estimation
Himangi Mittal,Brian Okorn,David Held +2 more
- 14 Jun 2020
TL;DR: This work presents a method of training scene flow that uses two self-supervised losses, based on nearest neighbors and cycle consistency, which matches current state-of-the-art supervised performance using no real world annotations and exceeds state- of- the-art performance when combining the self- supervised approach with supervised learning on a smaller labeled dataset.
Using laser scanners for modeling and analysis in architecture, engineering, and construction
Daniel Huber,Burcu Akinci,Pingbo Tang,Antonio Adán,Brian Okorn,Xuehan Xiong +5 more
- 17 Mar 2010
TL;DR: This paper provides an overview of the cross-disciplinary research team's recent research efforts, which includes improving the understanding of the low-level aspects of laser scanner data, using comparison methods to analyze laser scanners data and derived models, and developing modeling and recognition algorithms to support the automatic creation of building models from laser scan data.
71
ZePHyR: Zero-shot Pose Hypothesis Rating
Brian Okorn,Qiao Gu,Martial Hebert,David Held +3 more
- 30 May 2021
TL;DR: Zephyr et al. as mentioned in this paper used a hypothesis generation and scoring framework, with a focus on learning a scoring function that generalizes to objects not used for training and achieved zero-shot generalization by rating hypotheses as a function of unordered point differences.
32
Cloth Region Segmentation for Robust Grasp Selection
Jianing Qian,Thomas Weng,Luxin Zhang,Brian Okorn,David Held +4 more
- 24 Oct 2020
TL;DR: In this paper, a network is trained to segment the edges and corners of a cloth from a depth image, distinguishing such regions from wrinkles or folds, and a novel algorithm is proposed to estimate the grasp location, direction, and directional uncertainty from the segmentation.
31
Cloth Region Segmentation for Robust Grasp Selection
TL;DR: This work trains a network to segment the edges and corners of a cloth from a depth image, distinguishing such regions from wrinkles or folds, and provides a novel algorithm for estimating the grasp location, direction, and directional uncertainty from the segmentation.
28